Task-Oriented Adaptive Distributed Node State Exchange Framework in Mobile Edge Networks

With the development of mobile edge computing, task collaboration among edge nodes is an effective way to address the limited edge resources. The critical step in resource collaboration is obtaining and updating edge nodes eligible for collaboration. However, the dynamic nature of the mobile edge network makes acquiring an accurate and timely node state challenging. This paper introduces a Task-oriented Adaptive Distributed (TAD) node state exchange framework to improve network service quality and system energy efficiency. Two main components of the TAD framework are the Scheduled State Update (SSU) Algorithm, which periodically maintains state information, and the Task-driven Resource Discovery (TRD) Algorithm, which updates outdated information to ensure the network adapts to changes. In addition, the Adaptive Dynamic Counter (ADC) is designed to make the update frequency of SSU dynamically adjustable according to the task execution and node state. The framework significantly improves the task completion rate and reduces energy consumption. Compared to the existing state-of-the-art methods, the task completion rate demonstrates an improvement of up to 36.70%, while the energy consumption exhibits a reduction rate of up to 33.38%.